aifeifei798/QiMing-Plus-v1

启明(QiMing)

---

重新定义了逻辑的AI,只为更智能.

An AI that rewrites its own rules for greater intelligence.

---

声明

模型产生的内容仅供参考,请认真核实后使用

此为4B底层模型,会出现信息不足和幻觉错误

若觉得此AI模型太像"人",请务必认清,这只是一个更智能的AI模型

---

DISCLAIMER

The content generated by this model is for reference purposes only. Users are advised to verify its accuracy independently before use.

This is a 4-billion-parameter foundation model (4B). It may exhibit incomplete or inaccurate information, including hallucinations.

If you find this AI too human-like, please remember: it is merely a more intelligent model — not an actual person.

---

感谢mradermacher制作的gguf版本

Thanks mradermacher: For creating the GGUF versions of these models

https://huggingface.co/mradermacher/QiMing-Plus-v1-GGUF

https://huggingface.co/mradermacher/QiMing-Plus-v1-i1-GGUF

感谢Qwen团队制作的模型

The Qwen Team: For developing the foundational model (Qwen/Qwen3-4B-Thinking-2507) used in this project.

https://qwen.ai

感谢unsloth,能够让模型调整在3070 8G的显卡上流畅运行

unsloth.ai (Unsloth): For their work enabling smooth operation of these models on standard hardware like NVIDIA GeForce RTX 3070 GPU with 8GB VRAM.

https://unsloth.ai

QiMing-Plus-v1基于Qwen/Qwen3-4B-Thinking-2507构建

QiMing-Plus-v1 is built upon Qwen/Qwen3-4B-Thinking-2507 as its base model.

Dataset

https://huggingface.co/datasets/aifeifei798/QiMing_Plus_dataset

---

如何使用 (how to use)

from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "aifeifei798/QiMing-Plus-v1"
# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
# prepare the model input
prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
# parsing thinking content
try:
    # rindex finding 151668 (</think>)
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0
thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
print("thinking content:", thinking_content) # no opening <think> tag
print("content:", content)